Triple
T28247007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Burgundy wine region |
E712194
|
entity |
| Predicate | hasNotableGrandCru |
P12904
|
FINISHED |
| Object | Romanée-Conti |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Romanée-Conti | Statement: [Burgundy wine region, hasNotableGrandCru, Romanée-Conti]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableGrandCru Context triple: [Burgundy wine region, hasNotableGrandCru, Romanée-Conti]
-
A.
hasGrandCru
chosen
Indicates that an entity possesses, is associated with, or includes a wine classified as Grand Cru.
-
B.
hasNoGrandCruVineyards
Indicates that the subject entity does not possess, include, or encompass any vineyards classified as Grand Cru.
-
C.
hasPremierCruClassé
Indicates that an entity holds or is assigned a Premier Cru Classé classification or status.
-
D.
recognizedAsGrandCruSince
Indicates that an entity has held the official status or classification of Grand Cru starting from a specified point in time.
-
E.
notablePremierCru
Indicates that a subject is recognized as a distinguished or especially noteworthy Premier Cru within its classification.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69efb51fb98881909692421959ec0170 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69ff109695008190a22b47ef8be2e3f9 |
completed | May 9, 2026, 10:46 a.m. |
| PD | Predicate disambiguation | batch_69ff0f243ea88190970d2c520b55c816 |
completed | May 9, 2026, 10:40 a.m. |
Created at: April 27, 2026, 11:02 p.m.